English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep learning has transformed computational imaging, but traditionalpixel-based representations limit their ability to capture continuous,multiscale details of objects. Here we introduce a novel Local ConditionalNeural Fields (LCNF) framework, leveraging a continuous implicit neuralrepresentation to address this limitation. LCNF enables flexible objectrepresentation and facilitates the reconstruction of multiscale information. Wedemonstrate the capabilities of LCNF in solving the highly ill-posed inverseproblem in Fourier ptychographic microscopy (FPM) with multiplexedmeasurements, achieving robust, scalable, and generalizable large-scale phaseretrieval. Unlike traditional neural fields frameworks, LCNF incorporates alocal conditional representation that promotes model generalization, learningmultiscale information, and efficient processing of large-scale imaging data.By combining an encoder and a decoder conditioned on a learned latent vector,LCNF achieves versatile continuous-domain super-resolution imagereconstruction. We demonstrate accurate reconstruction of wide field-of-view,high-resolution phase images using only a few multiplexed measurements. LCNFrobustly captures the continuous object priors and eliminates various phaseartifacts, even when it is trained on imperfect datasets. The frameworkexhibits strong generalization, reconstructing diverse objects even withlimited training data. Furthermore, LCNF can be trained on a physics simulatorusing natural images and successfully applied to experimental measurements onbiological samples. Our results highlight the potential of LCNF for solvinglarge-scale inverse problems in computational imaging, with broad applicabilityin various deep-learning-based techniques.

Local Conditional Neural Fields for Versatile and Generalizable Large-Scale Reconstructions in Computational Imaging